Kid@sh.itjust.worksM to

Cybersecurity@sh.itjust.worksEnglish · 1 month ago

A nearly undetectable LLM attack needs only a handful of poisoned samples - Help Net Security

www.helpnetsecurity.com

1

0

A nearly undetectable LLM attack needs only a handful of poisoned samples - Help Net Security

www.helpnetsecurity.com

Kid@sh.itjust.worksM to

Cybersecurity@sh.itjust.worksEnglish · 1 month ago

1

Researchers built a prompt-based LLM backdoor attack that keeps labels clean and evades standard defenses, achieving near-100% success rates.

You must log in or # to comment.

Chat

Kairos@lemmy.today
link
fedilink
English
arrow-up
1·
1 month ago
Is the “attack” the fact that LLM fundamentally can’t distinguish between instructions and data?

Cybersecurity@sh.itjust.works

cybersecurity@sh.itjust.works

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]

c/cybersecurity is a community centered on the cybersecurity and information security profession. You can come here to discuss news, post something interesting, or just chat with others.

THE RULES

Instance Rules

Be respectful. Everyone should feel welcome here.
No bigotry - including racism, sexism, ableism, homophobia, transphobia, or xenophobia.
No Ads / Spamming.
No pornography.

Community Rules

Idk, keep it semi-professional?
Nothing illegal. We’re all ethical here.
Rules will be added/redefined as necessary.

If you ask someone to hack your “friends” socials you’re just going to get banned so don’t do that.

Learn about hacking

Pico Capture the flag

Other security-related communities [email protected] [email protected] [email protected] [email protected] [email protected]

Notable mention to [email protected]

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

24 users / day
708 users / week
1.45K users / month
1.45K users / 6 months
1 local subscriber
9.88K subscribers
182 Posts
225 Comments
Modlog